Channels and Features Identification: A Review and a Machine-Learning Based Model With Large Scale Feature Extraction for Emotions and ASD Classification.

Autism Spectrum Disorder (ASD) is characterized by impairments in social and cognitive skills, emotional disorders, anxiety, and depression. The prolonged conventional ASD diagnosis raises the sheer need for early meaningful intervention. Recently different works have proposed potential for ASD diagnosis and intervention through emotions prediction using deep neural networks (DNN) and machine learning algorithms. However, these systems lack an extensive large-scale feature extraction (LSFE) analysis through multiple benchmark data sets. LSFE analysis is required to identify and utilize the most relevant features and channels for emotion recognition and ASD prediction. Considering these challenges, for the first time, we have analyzed and evaluated an extensive feature set to select the optimal features using LSFE and feature selection algorithms (FSA). A set of up to eight most suitable channels was identified using different best-case FSA. The subject-wise importance of channels and features is also identified. The proposed method provides the best-case accuracies, precision, and recall of 95, 92, and 90%, respectively, for emotions prediction using a linear support vector machine (LSVM) classifier. It also provides the best-case accuracy, precision, and recall of 100% for ASD classification. This work utilized the largest number of benchmark data sets (5) and subjects (99) for validation reported till now in the literature. The LSVM classification algorithm proposed and utilized in this work has significantly lower complexity than the DNN, convolutional neural network (CNN), Naïve Bayes, and dynamic graph CNN used in recent ASD and emotion prediction systems.

A 10.13µJ/Classification 2-Channel Deep Neural Network Based SoC for Negative Emotion Outburst Detection of Autistic Children.

An electroencephalogram (EEG)-based non-invasive 2-channel neuro-feedback SoC is presented to predict and report negative emotion outbursts (NEOB) of Autistic patients. The SoC incorporates area-and-power efficient dual-channel Analog Front-End (AFE), and a deep neural network (DNN) emotion classification processor. The classification processor utilizes only the two-feature vector per channel to minimize the area and overfitting problems. The 4-layers customized DNN classification processor is integrated on-sensor to predict the NEOB. The AFE comprises two entirely shared EEG channels using sampling capacitors to reduce the area by 30%. Moreover, it achieves an overall integrated input-referred noise, NEF, and crosstalk of 0.55 µVRMS, 2.71, and -79 dB, respectively. The 16 mm2 SoC is implemented in 0.18 um 1P6M, CMOS process and consumes 10.13 µJ/classification for 2 channel operation while achieving an average accuracy of >85% on multiple emotion databases and real-time testing.

An On-Chip Processor for Chronic Neurological Disorders Assistance Using Negative Affectivity Classification.

Chronic neurological disorders (CND's) are lifelong diseases and cannot be eradicated, but their severe effects can be alleviated by early preemptive measures. CND's, such as Alzheimer's, Autism Spectrum Disorder (ASD), and Amyotrophic Lateral Sclerosis (ALS), are the chronic ailment of the central nervous system that causes the degradation of emotional and cognitive abilities. Long term continuous monitoring with neuro-feedback of human emotions for patients with CND's is crucial in mitigating its harmful effect. This paper presents hardware efficient and dedicated human emotion classification processor for CND's. Scalp EEG is used for the emotion's classification using the valence and arousal scales. A linear support vector machine classifier is used with power spectral density, logarithmic interhemispheric power spectral ratio, and the interhemispheric power spectral difference of eight EEG channel locations suitable for a wearable non-invasive classification system. A look-up-table based logarithmic division unit (LDU) is to represent the division features in machine learning (ML) applications. The implemented LDU minimizes the cost of integer division by 34% for ML applications. The implemented emotion's classification processor achieved an accuracy of 72.96% and 73.14%, respectively, for the valence and arousal classification on multiple publicly available datasets. The 2 x 3mm2 processor is fabricated using a 0.18 µm 1P6M CMOS process with power and energy utilization of 2.04 mW and 16 µJ/classification, respectively, for 8-channel operation.